The pure exploration problem with general reward functions depending on full distributions

DOI10.1007/S10994-022-06214-8MaRDI QIDQ2102381zbMATH OpenOpenAlexFDO

Authors Yanyan Li

Publication date 28 November 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2105.03598

zbMATH Keywords

general reward functionpure explorationtotal variation distance

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A simple and effective scanning rule for a multi-channel system
• Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems
• Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator
• Extremum Problems With Total Variation Distance and Their Applications
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 4078557 (Why is no real title available?)
• scientific article; zbMATH DE number 1015853 (Why is no real title available?)
• Multi-armed bandit allocation indices. With a foreword by Peter Whittle.
• On a Problem in Optimal Scanning
• On Choosing and Bounding Probability Metrics
• On the complexity of best-arm identification in multi-armed bandit models
• Reinforcement learning. An introduction
• Sequential Design of Experiments
• The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality

This page was built for publication: The pure exploration problem with general reward functions depending on full distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2102381)